dolthub/dolt
Dolt is a SQL database with Git-like version control capabilities, enabling users to manage, version, and collaborate on data and schemas as easily as code in Git repositories.
Canner/WrenAI
WrenAI is an open-source generative business intelligence engine from Canner, written mainly in Python and licensed under Apache 2.0. It turns natural-language questions into governed SQL and into dashboards and charts across more than twenty data sources, among them BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift and Databricks. The core, the SDK, the CLI, the connectors and an MCP server are open source, so agents such as Claude Code or Cursor reach Wren over MCP and use it as a governed query layer instead of guessing at SQL. Correctness rests on two layers underneath generation: a semantic layer expressed in a modelling definition language that records business meaning, approved definitions, units, enumerations and joins, and an AI context layer that adds company knowledge from documents, wikis and chat threads plus a memory of examples that worked. Both are stored as version-controlled files that can be reviewed in Git rather than hidden in prompts or locked in a vendor interface. Generation is guarded by schema-aware retrieval, planning against the semantic model, dry-plan validation, row limits, structured errors with hints, value profiling and an evaluation runner. Any answer can be turned into a browser-side dashboard powered by a WebAssembly build of the query core and shipped to a Vercel or Cloudflare Pages account with one command. Installation is a pip package with per-datasource extras, followed by a small discovery stub installed into the AI client that teaches the agent to fetch workflow guides from the CLI. The Wren Engine now lives in the same repository, and the earlier Docker-based chat-first product is preserved on a legacy branch. Row-level and column-level security and access control are reserved for the cloud and self-hosted editions.
https://github.com/Canner/WrenAI
Also in Databases
t8y2/dbx
DBX is a lightweight, cross-platform database client supporting over 70 databases, featuring a built-in AI assistant, MCP Server, and available as desktop, Docker, or CLI.
googleapis/mcp-toolbox
MCP Toolbox for Databases is an open-source Model Context Protocol (MCP) server that connects AI agents, IDEs, and applications directly to enterprise databases, offering both pre-built and custom ...
makenotion/notion-mcp-server
The Notion MCP Server is an official MCP server implementation that enables secure, programmatic interaction with Notion content through MCP commands, optimized for AI agents and supporting multiple deployment options.
bytebase/dbhub
DBHub is a universal database gateway implementing the Model Context Protocol (MCP) server interface, enabling MCP clients to connect to and explore multiple database systems including MySQL, PostgreSQL, Oracle, SQL Server, MariaDB, and SQLite.
crystaldba/postgres-mcp
Postgres MCP Pro is an open-source Model Context Protocol server for PostgreSQL that provides advanced database health monitoring, index tuning, query plan analysis, and safe SQL execution to support AI agents and developers throughout the application lifecycle.
supabase-community/supabase-mcp
Supabase MCP Server connects Supabase projects to AI assistants using the Model Context Protocol, enabling LLMs to manage and query Supabase resources.
benborla/mcp-server-mysql
mcp-server-mysql is a Model Context Protocol server that provides secure, read-only access to MySQL databases, enabling large language models to inspect schemas and execute SQL queries efficiently.